© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 44884
    Prev
    Next
    INDEX
    Explanations

    legal judgments and discretion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minimal
    -0.07
     commonplace
    -0.07
    来形容
    -0.07
    什么意思
    -0.07
     Chance
    -0.07
     opener
    -0.07
     jButton
    -0.06
    obutton
    -0.06
     Brigade
    -0.06
     Means
    -0.06
    POSITIVE LOGITS
    _TRIANGLES
    0.07
    瑧
    0.07
     ואח
    0.07
    terror
    0.07
    FilterWhere
    0.07
    囿
    0.06
    倮
    0.06
     IMAGE
    0.06
    签下
    0.06
     فأ
    0.06
    Activations Density 0.014%

    No Known Activations